Utilizing artificial neural networks for WLAN positioning

Abstract

Short range wireless technologies such as WLAN, Bluetooth, RFID, ultrasound and IrDA can be used to supply location information in indoor areas in which their coverage is assured. With respect to outdoor techniques, these technologies are more accurate but with smaller covering areas. In this paper, we present the comparison of the existing location techniques in WLAN networks and a novel approach of utilizing artificial neural networks for positioning purposes. In addition to estimating WLAN client's position, neural networks have been employed to estimate the room and type of the room the client resides in. Extensive measurements were conducted to evaluate these approaches and the obtained results indicate performances sufficient for real case use.